• 대한기계학회논문집A
• /
• 제24권9호
• /
• pp.2283-2291
• /
• 2000

The neural network method is applied to automatically measure the crack opening load under random loading. The crack opening results obtained are compared with the visual measured results. Fatigue crack growth under random loading is predicted using the crack opening data measured by the neural network method, and the prediction results are compared with experimental ones. It is found that the neural network method can be successfully applied to consistently measure the crack opening load under random loading and also gives some results different from the results by visual measurement.

• 한국건설관리학회:학술대회논문집
• /
• 한국건설관리학회 2004년도 제5회 정기학술발표대회 논문집
• /
• pp.561-564
• /
• 2004

국내외에서는 크랙실링 공법의 이점 및 도로면 유지보수 공사의 위험 요소를 인식하여 90년대 초반부터 크랙실링 자동화 장비 개발을 위한 연구를 진행하여 왔다. 기존 문헌 고찰과 도로면 크랙실링 자동화 장비(Automated Pavement Crack Sealer; APCS)의 실험실 및 현장 실험 결과, 도로면에 존재하는 크랙 네트워크를 자동으로 탐지하고 모델링하는 과정의 속도와 정확성을 향상시키는 것은 개발된 크랙실링 자동화 장비의 실용화를 위해 매우 중요한 요인으로 인식되었다 그러나, CCD 카메라를 통해 습득된 도로면 영상에서 크랙 네트워크를 완전 자동으로 인식하는 기술은 일반적인 영상 인식 분야에서 보다 외부 환경적인 요인으로 인해 낮은 인식률을 가지고 있다 본 연구를 통해 기존에 개발된 APCS 머신비전 알고리즘의 경우 도로면 영상의 환경 요인에 의해 발생된 문제점들을 많이 해결하였으나 실용화 단계에서 요구되는 크랙 인식률에는 도달하지 못하였다. 따라서, 본 연구의 목적은 기존 APCS 머신 비전 알고리즘의 완전 자동화 방식 크랙 탐지 및 모델링 알고리즘의 문제점을 분석하고 신경망 학습 기법을 이용한 크랙 인식 알고리즘을 개발하는 것이다.

• 제어로봇시스템학회논문지
• /
• 제11권4호
• /
• pp.290-296
• /
• 2005

This paper presents the implementation of a crack tracking mobile robot. The crack tracking robot is built for tracking cracks on the pavement. To track cracks, crack must be detected by laser and camera sensors. Laser sensor projects laser on the pavement to detect the discontinuity on the surface and the camera captures the image to find the crack position. Then the robot is commanded to follow the crack. To detect crack position correctly, neural network is used to minimize the positional errors of the captured crack position obtained by transformation from 2 dimensional images to 3 dimensional images.

• Geomechanics and Engineering
• /
• 제21권6호
• /
• pp.537-549
• /
• 2020

The presence of cracks changes the water content pattern during seepage through a cracked soil as compared to that of intact soil. In addition, several different crack networks may form in one soil type. These two factors result in a variation of water contents in the soil matrix part of a cracked soil during seepage. This paper presents an investigation of the effect of crack network representation on the water content of the soil matrix part of cracked soil using numerical models. A new method for the numerical generation of crack networks incorporating connections among crack endpoints was developed as part of the investigation. Numerical analysis results indicated that the difference in the point water content was large, whereas the difference in the average water content was relatively small, indicating the uniqueness of the crack network representation on the average water content of the soil matrix part of cracked soil.

• Computers and Concrete
• /
• 제32권6호
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Smart Structures and Systems
• /
• 제30권1호
• /
• pp.17-34
• /
• 2022

For steel structures, fatigue cracks are critical damage induced by long-term cycle loading and distortion effects. Vision-based crack detection can be a solution to ensure structural integrity and performance by continuous monitoring and non-destructive assessment. A critical issue is to distinguish cracks from other features in captured images which possibly consist of complex backgrounds such as handwritings and marks, which were made to record crack patterns and lengths during periodic visual inspections. This study presents a parametric study on image-based crack identification for orthotropic steel bridge decks using captured images with complicated backgrounds. Firstly, a framework for vision-based crack segmentation using the atrous convolution-based Deeplapv3+ network (ACDN) is designed. Secondly, features on crack images are labeled to build three databanks by consideration of objects in the backgrounds. Thirdly, evaluation metrics computed from the trained ACDN models are utilized to evaluate the effects of obstacles on crack detection results. Finally, various training parameters, including image sizes, hyper-parameters, and the number of training images, are optimized for the ACDN model of crack detection. The result demonstrated that fatigue cracks could be identified by the trained ACDN models, and the accuracy of the crack-detection result was improved by optimizing the training parameters. It enables the applicability of the vision-based technique for early detecting tiny fatigue cracks in steel structures.

• 대한기계학회논문집A
• /
• 제24권1호
• /
• pp.52-61
• /
• 2000

The role of quantitative nondestructive evaluation of defects is becoming more important to assure the reliability and the safety of structure, which can eventually be used for residual life evaluation of structure on the basis of fracture mechanics approach. Although ultrasonic technique is one of the most widely used techniques for application of practical field test among the various nondestructive evaluation technique, there are still some problems to be solved in effective extraction and classification of ultrasonic signal from their noisy ultrasonic waveforms. Therefore, crack size determination through a neural network based on the back-propagation algorithm using back-scattered ultrasonic signals is established in this study. For this purpose, aluminum plate containing vertical or inclined surface breaking crack with different crack length was used to receive the back-scattered ultrasonic signals by pulse echo method. Some features extracted from these signals and sizes of cracks were used to train neural network and the neural network's output of the crack size are compared with the true answer.

• Computers and Concrete
• /
• 제26권5호
• /
• pp.411-420
• /
• 2020

Deep Convolution neural network (DCNN) has been widely used in the healthy maintenance of civil infrastructure. Using DCNN to improve crack detection performance has attracted many researchers' attention. In this paper, a light-weight spatial attention network module is proposed to strengthen the representation capability of ResNet and improve the crack detection performance. It utilizes attention mechanism to strengthen the interested objects in global receptive field of ResNet convolution layers. Global average spatial information over all channels are used to construct an attention scalar. The scalar is combined with adaptive weighted sigmoid function to activate the output of each channel's feature maps. Salient objects in feature maps are refined by the attention scalar. The proposed spatial attention module is stacked in ResNet50 to detect crack. Experiments results show that the proposed module can got significant performance improvement in crack detection.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2022년도 가을 학술논문 발표대회
• /
• pp.245-246
• /
• 2022

Typically, the methods of crack detection on concrete structures include some problems, such as a low accuracy and expensive. To solve these problems, we proposed a neural network-based crack search method. The proposed algorithm goes through three convolutions and is classified into crack and non-crack through the softmax layer. As a result of the performance evaluation, cracks can be detected with an accuracy of 99.4 and 99.34 % at the training model and the validation model, respectively.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.354-366
• /
• 2020

This work mainly focuses on determination of the fully plastic J-integral solutions for welded center cracked plates subjected to remote tension loading. Detailed three-dimensional elasticeplastic Finite Element Analyses (FEA) were implemented to compute the fully plastic J-integral along the crack front for a wide range of crack geometries, material properties and weld strength mismatch ratios for 900 cases. According to the database generated from FEA, Back-propagation Neural Network (BPNN) model was proposed to predict the values and distributions of fully plastic J-integral along crack front based on the variables used in FEA. The determination coefficient R2 is greater than 0.99, indicating the robustness and goodness of fit of the developed BPNN model. The network model can accurately and efficiently predict the elastic-plastic J-integral for weld centerline crack, which can be used to perform fracture analyses and safety assessment for welded center cracked plates with varying strength mismatch conditions under uniaxial loading.